© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3200
    Prev
    Next
    INDEX
    Explanations

    vitamin E

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Sig
    -0.24
    é«Ń
    -0.23
    æ¼Ķå¥ı
    -0.23
    Sig
    -0.22
     mine
    -0.22
     Colon
    -0.22
    们çļĦ
    -0.21
    EFI
    -0.21
    /logs
    -0.21
    们
    -0.21
    POSITIVE LOGITS
    olith
    0.26
    åħ¼é¡¾
    0.24
    ä¼´éļı
    0.23
    Ub
    0.23
    Oil
    0.23
     oils
    0.23
    è´Łè´£äºº
    0.22
    æ²¹
    0.22
     promin
    0.22
    cake
    0.22
    Activations Density 0.002%

    No Known Activations